Tagged: Agents
8 posts
Your Task Manager Is the Best Agent Memory You're Not Using
Agent memory without a new vector DB. Your task app is years of curated, ranked context. ATS gives your agent a hybrid-retrieval channel into it.
Build the Harness Once With Your Best Model. Run It on a Cheap One.
Agents forget and good ones cost. The fix is not a better model. Put the goal in deterministic scripts and run a cheap model against them.
Most of Your AI Skills Will Rot. Here's Which Ones Compound.
A skill's lifespan is set by what it couples to, not how good the prompt is. Why most AI skills rot, which parts compound, and how to tell.
Agentic Knowledge Base — Karpathy's LLM wiki, with adapters
A framework that turns whatever task or note app you use into a Karpathy-style LLM wiki. Pluggable adapters, parallel retrieval with RRF.
What Anthropic's April 23 Postmortem Reveals About Your Agent Harness
Three bugs over two months, one usage-limit reset for every Pro subscriber. The postmortem reads like a free audit checklist for any production agent harness.
Claude Code SDK Agents: Build Production Agents Without the Loop
Claude Code SDK agents give you file tools, bash, MCP, and subagents for free. Here's when to use the SDK vs the raw Claude API, with real code. Download the free AI Automation Checklist.
Claude Extended Thinking: How budget_tokens Is Billed (Real Costs)
Extended thinking bills as output tokens. What budget_tokens controls, real cost per request, and the Node.js setup with a copyable cost table.
AI Skills Are the New Boilerplate: They Fix Nothing
Everyone shares skill libraries now. Why the 20-slash-command pitch and the 2-hours-saved claim miss what actually ships value in production. Book a free discovery call.